@inbook{dd52effae15b412a9c2f50bd8a8a43f0,
title = "Bert and approximate string matching for automatic recognition and normalization of professions in spanish medical documents",
abstract = "This publication presents the participation of the EdIE-KnowLab team in the MEDical DOcuments PROFessions recognition shared task from IberLeF 2021. The proposed system consists of a Spanish version of the BERT classification model, BETO, for the Named Entity Recognition tasks and an approximate string matching technique using Damerau{ Levenshtein distance for the Normalization task. The NER systems reached 64.3% and 60.4% in Micro-Average F1 for Task 1 and Task 2, respectively. The approximate string matching approach obtained 17.8% in F1 for the Normalization task. Source code to reproduce the results is available under the MIT license at https://github.com/ vsuarezpaniagua/EdIE-MEDDOPROF.",
keywords = "BERT, Damerau{Levenshtein, Deep Learning, Medical Documents, Named Entity Recognition, Normalization",
author = "V{\'i}ctor Su{\'a}rez-Paniagua and Arlene Casey",
note = "Funding Information: The authors would like to thank to members in the Clinical Natural Language Processing Research Group and KnowLab in the University of Edinburgh and University College London for their valuable discussion and comments. This work was supported by the HDR UK National Text Analytics Implementation Project, Wellcome Institutional Translation Partnership Awards (PIII029), a Legal and General PLC (research grant to establish the independent Advanced Care Research Centre at University of Edinburgh). Legal and General PLC had no role in conduct of the study, interpretation or the decision to submit for publication. The views expressed are those of the authors and not necessarily those of Legal and General PLC. Publisher Copyright: {\textcopyright} 2021 CEUR-WS. All rights reserved.; 2021 Iberian Languages Evaluation Forum, IberLEF 2021 ; Conference date: 21-09-2021",
year = "2021",
month = sep,
day = "21",
language = "English",
volume = "2943",
series = "CEUR Workshop Proceedings",
publisher = "CEUR-WS",
pages = "803--813",
booktitle = "IBER LEF 2021",
}